AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2

Faisal Bin Ashraf; Animesh Ray; Stefano Lonardi

q-bio.QMMar 4, 2026

AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2

Authors: Faisal Bin Ashraf, Animesh Ray, Stefano Lonardi

Organizations: Department of Computer Science and Engineering,University of California, Riverside, 92521, CA, United States · Riggs School of Applied Life Sciences, Keck Graduate Institute, Claremont, 91711, CA, United States

Abstract

Machine learning-based antibody design is emerging as one of the most promising approaches to combat infectious diseases, due to significant advancements in the field of artificial intelligence and an exponential surge in experimental antibody data (in particular related to COVID-19). The ability of an antibody to bind to an antigens (called binding affinity) is one of the the most critical properties in designing neutralizing antibodies. In this study we introduce Ab-Affinity, a new large language model that can accurately predict the binding affinity of antibodies against a target peptide, e.g., the SARS-CoV-2 spike protein. Code and model are available at https://github.com/ucrbioinfo/AbAffinity.

Figures & tables

Figure 1: Overview of Ab-Affinity. Ab-Affinity predicts the binding affinity against a specific target peptide; it can also provide residue-residue contact maps and an embedding of the input sequence.

Figure 2: Dataset description. a. Distribution of Binding Affinity ( $\log~K_{D}$ ); b. Distribution of antibodies from each seed; c. Distribution of antibodies with mutation.

Figure 3: Model Architecture of Ab-Affinity

Figure 4: Comparing affinity prediction models: (a) Pearson and Spearman correlation for DG-Affinity (p-values = $3.86\times 10^{-14}$ , and $3.38\times 10^{-15}$ ), ESM-2 (p-values = $8.03\times 10^{-198}$ , and $8.02\times 10^{-198}$ ), AbLang (p-values = $1.24\times 10^{-175}$ , and $1.02\times 10^{-163}$ ) and Ab-Affinity (p-values = $4.03\times 10^{-261}$ , and $8.65\times 10^{-217}$ ); scatter plot for actual vs. predicted binding affinity for (b) DG-Affinity, (c) ESM-2, (d) AbLang, (e) Ab-Affinity (includes antibodies for all three seeds)

Figure 5: t-SNE representation of the embedding produced by ESM-2 and Ab-Affinity; antibodies are colored according to their predicted binding affinity.

Model	Ref	14H		14L
Model	Ref	Pearson	Spearman	Pearson	Spearman
Ens-Grad	[ 10 ]	0.601	0.476	0.637	0.645
ESM-F	[ 6 ]	0.634	0.516	0.674	0.681
AntiBERTa2	[ 2 ]	0.623	0.545	0.673	0.684
AbMAP	[ 17 ]	0.606	0.510	0.674	0.685
A2Binder	[ 6 ]	0.642	0.553	0.683	0.688

Table 1: Comparing Ab-Affinity against other binding affinity predictors on 14H and 14L dataset

Figure 6: ROC curves and AUC values for two classification tasks, namely (a,b) determining the binding affinity class of an antibody (High, Medium, Low) and (c,d) determining whether the binding is improved compared to the seed antibody (Y/N); (a,c) ROC curves using the ESM-2 embedding; (b,d) ROC curves using the Ab-Affinity embedding; AUC values are reported for each classifier

Figure 7: Differences between the attention residue-residue maps for strong binding (i.e. $\log K_{d}<0.5$ ) and weak binding (i.e., $\log K_{d}>5.5$ ) for antibodies generated from Ab-14 (a) heavy chain, and (b) light chain.

Figure 8: t-SNE visualization of the embeddings produced by ESM-2 and Ab-Affinity; points are colored according to the experimentally-determined thermostability of those antibodies

Protein Language Models

Protein language models learn patterns in amino-acid sequences to predict protein properties, interpret mutations, and design new proteins.

See all 69 papers

AbLWR:A Context-Aware Listwise Ranking Framework for Antibody-Antigen Binding Affinity Prediction via Positive-Unlabeled Learning
Apr 13, 2026Fan Xu, Zhi-an Huang, Haohuai He +5Learning to Rank
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China · Department of Computer Science, City University of Hong Kong (Dongguan), Dongguan, China · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China +1
DuaDeep-SeqAffinity: Dual-Branch Deep Learning for Tri-Stream Sequence-Based Antibody--Antigen Affinity Prediction
Dec 26, 2025Aicha Boutorh, Soumia Bouyahiaoui, Manel Kara Laouar +3Hybrid CNN-Transformer Architectures Molecular Property Prediction
National School of Artificial Intelligence (ENSIA) Sidi Abdallah Campus, Algiers, Algeria · Lamine Debaghine University Hospital Center, CHU Bab El Oued, Algiers, Algeria
Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
Jul 22, 2026Xiaoliang Shi, Zichen Wang, Runze Ma +2Multimodal Pretraining Protein Design
Shanghai Jiao Tong University

Apr 13, 2026J/K move · Enter open · S save

AbLWR:A Context-Aware Listwise Ranking Framework for Antibody-Antigen Binding Affinity Prediction via Positive-Unlabeled Learning

Fan Xu, Zhi-an Huang, Haohuai He, Yidong Song+4

Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China · Department of Computer Science, City University of Hong Kong (Dongguan), Dongguan, China · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China+1

Learning to Rank

Open paper AskPDF arXiv

Accurate prediction of antibody-antigen binding affinity is fundamental to therapeutic design, yet remains constrained by severe label sparsity and the complexity of antigenic variations. In this paper, we propose AbLWR (Antibody-antigen binding affinity List-Wise Ranking), a novel framework that reformulates the conventional affinity regression task as a listwise ranking problem. To mitigate label sparsity, AbLWR incorporates a PU (Positive-Unlabeled) learning mechanism leveraging a dual-level contrastive objective and meta-optimized label refinement to learn robust representations. Furthermore, we address antigenic variation by employing a homologous antigen sampling strategy where Multi-Head Self-Attention (MHSA) explicitly models inter-sample relationships within training lists to capture subtle affinity nuances. Extensive experiments demonstrate that AbLWR significantly outperforms state-of-the-art baselines, improving the Precision@1 (P@1) by over 10

\%

in randomized cross-validation experiments. Notably, case studies on Influenza and IL-33 validate its practical utility, demonstrating robust ranking consistency in distinguishing subtle viral mutations and efficiently prioritizing top-tier candidates for wet-lab screening.

Abstract

Protein Language Models

Explore similar work

AbLWR:A Context-Aware Listwise Ranking Framework for Antibody-Antigen Binding Affinity Prediction via Positive-Unlabeled Learning

DuaDeep-SeqAffinity: Dual-Branch Deep Learning for Tri-Stream Sequence-Based Antibody--Antigen Affinity Prediction

Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design